Repository navigation
worker: instructions lead with what memory is for; claim tool names feedback as what accepts - #87
Merged
Merged
Conversation
…ted claims before LIMIT
…-ghkdsb # Conflicts: # docs/features/hosted-worker.md # worker/src/mcp.ts # worker/src/memory.ts
…eedback as what accepts
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Requested by Vu · project thread
The MCP
initializeinstructions open with what memory is for (what the next agent would otherwise pay to rediscover; not status or what the code says) and keep each step to a line or two in plain case, instead of five capitalised procedures. The claim step asks forevidence(#86) and says an untested guess is not a lesson.Also fixes drift: the
claimtool description said a candidate is "accepted once another session claims the same subject", which contradicts the echo guard; it now names ausedrating viafeedback. The kypp README template and AGENTS.md block mentionevidence.Why: Anthropic's agent memory post found scripted write rules cut memory gains for capable models while a plain statement of purpose helped. kypp has no eval for instruction wording, so this is a hypothesis to watch in the usefulness report, not a measured win.
Contracts touched:
initializeinstructions text;claimtool description.Verification:
npm run typecheck;npm test388/388 (instruction assertions infeedback.test.tsupdated; read-only callers still never seeclaim);featuremap.py checkclean.Generated by Claude Code